fraQtl AI Research

company

https://fraQtl.ai

Activity Feed

AI & ML interests

KV cache compression, inference optimization, model compression

Recent Activity

samuel-salfati updated a model about 4 hours ago

fraQtl/Gemma-4-E2B-it-Hi-Fi-GGUF

samuel-salfati updated a Space 11 days ago

fraQtl/README

samuel-salfati updated a model 11 days ago

fraQtl/Qwen3.6-35B-A3B-compressed

View all activity

samuel-salfati

updated a model about 4 hours ago

fraQtl/Gemma-4-E2B-it-Hi-Fi-GGUF

Text Generation • 5B • Updated about 4 hours ago • 2.07k • 15

samuel-salfati

updated a Space 11 days ago

README

🚀

samuel-salfati

updated 6 models 11 days ago

updated a collection 16 days ago

Hi-Fi Quants — calibrated GGUFs with KLD receipts

Collection

Calibration-aware Q4-class GGUFs at identical size to leading community quants, with measured KLD receipts. • 4 items • Updated 16 days ago

samuel-salfati

published 2 models 17 days ago

fraQtl/Gemma-4-26B-A4B-it-Hi-Fi-GGUF

Text Generation • 25B • Updated 11 days ago • 347 • 1

fraQtl/Gemma-4-E2B-it-Hi-Fi-GGUF

Text Generation • 5B • Updated about 4 hours ago • 2.07k • 15

samuel-salfati

updated 2 collections 19 days ago

Hi-Fi Quants — calibrated GGUFs with KLD receipts

Collection

Calibration-aware Q4-class GGUFs at identical size to leading community quants, with measured KLD receipts. • 4 items • Updated 16 days ago

KV-Cache Receipts — 3× the 128K users per A100 (vLLM)

Collection

Three-arm, needle-gated serving receipts (fp16 / fp8-KV / compressed) — reproducible for ≈$12 with one command. • 3 items • Updated 19 days ago

samuel-salfati

published 3 models about 1 month ago

fraQtl/fraqtl-sm80-runtime

Updated 11 days ago

fraQtl/qwen3-4b-instruct-2507-kv-sidecars

Updated 11 days ago

fraQtl/mistral-7b-instruct-v0.3-kv-sidecars

Updated 11 days ago

AI & ML interests

Recent Activity

Team members 1

fraQtl's activity

README